Instructions to use shivamjha98/Agnes-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shivamjha98/Agnes-8B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="shivamjha98/Agnes-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("shivamjha98/Agnes-8B", dtype="auto")

llama-cpp-python

How to use shivamjha98/Agnes-8B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="shivamjha98/Agnes-8B",
	filename="Agnes-8B-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use shivamjha98/Agnes-8B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf shivamjha98/Agnes-8B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf shivamjha98/Agnes-8B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf shivamjha98/Agnes-8B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf shivamjha98/Agnes-8B:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf shivamjha98/Agnes-8B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf shivamjha98/Agnes-8B:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf shivamjha98/Agnes-8B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf shivamjha98/Agnes-8B:Q4_K_M

Use Docker

docker model run hf.co/shivamjha98/Agnes-8B:Q4_K_M

LM Studio
Jan

vLLM

How to use shivamjha98/Agnes-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shivamjha98/Agnes-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shivamjha98/Agnes-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shivamjha98/Agnes-8B:Q4_K_M

SGLang

How to use shivamjha98/Agnes-8B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "shivamjha98/Agnes-8B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shivamjha98/Agnes-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "shivamjha98/Agnes-8B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shivamjha98/Agnes-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use shivamjha98/Agnes-8B with Ollama:
```
ollama run hf.co/shivamjha98/Agnes-8B:Q4_K_M
```

Unsloth Studio new

How to use shivamjha98/Agnes-8B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for shivamjha98/Agnes-8B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for shivamjha98/Agnes-8B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for shivamjha98/Agnes-8B to start chatting

Pi new

How to use shivamjha98/Agnes-8B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf shivamjha98/Agnes-8B:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "shivamjha98/Agnes-8B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use shivamjha98/Agnes-8B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf shivamjha98/Agnes-8B:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default shivamjha98/Agnes-8B:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use shivamjha98/Agnes-8B with Docker Model Runner:
```
docker model run hf.co/shivamjha98/Agnes-8B:Q4_K_M
```

Lemonade

How to use shivamjha98/Agnes-8B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull shivamjha98/Agnes-8B:Q4_K_M

Run and chat with the model

lemonade run user.Agnes-8B-Q4_K_M

List all available models

lemonade list

Agnes-8B — Bilingual (EN/JP) Personal AI Assistant

Agnes is a fine-tuned Qwen3-8B model designed as a bilingual (English/Japanese) personal AI assistant. She is polite, witty, and proactive — inspired by Jarvis from Iron Man. Agnes also serves as a Japanese language tutor and naturally code-switches between English and Japanese.

Model Details


Base Model	Qwen/Qwen3-8B
Method	LoRA (Low-Rank Adaptation) via PEFT
Parameters	8.2B total, 87M trainable (1.1%)
Precision	bfloat16
Context Length	4,096 tokens
Languages	English, Japanese

Available Files

File	Size	Use Case
`Agnes-8B-bf16.gguf`	~16 GB	Full precision — for powerful hardware or re-quantization
`Agnes-8B-Q4_K_M.gguf`	~5 GB	Quantized — for Raspberry Pi, Mac, or mobile devices

You can quantize the bf16 GGUF locally to other formats using llama.cpp:

llama-quantize Agnes-8B-bf16.gguf Agnes-8B-Q5_K_M.gguf Q5_K_M  # ~5.5GB, good balance
llama-quantize Agnes-8B-bf16.gguf Agnes-8B-Q3_K_M.gguf Q3_K_M  # ~3.5GB, smaller but lower quality

Training Details

Data

9,130 examples (80.5% Japanese, 19.5% English)
~550 hand-written conversational examples with Agnes's personality
~8,600 examples from 11 HuggingFace datasets (see dataset tags above)
Format: ChatML (system/user/assistant messages)

Hyperparameters

Parameter	Value
LoRA rank	32
LoRA alpha	64
Target modules	q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Learning rate	2e-5
Epochs	5
Batch size	8 x 4 (gradient accumulation) = 32 effective
Scheduler	Cosine with 5% warmup
Max seq length	4,096
Gradient checkpointing	Enabled
Attention	SDPA (PyTorch built-in)

Hardware

GPU: NVIDIA RTX PRO 6000 Blackwell (102 GB VRAM)
Training time: ~2.5 hours
Cloud: Runpod

Benchmark Results

Evaluated using lm-evaluation-harness on the Japanese Leaderboard tasks (full dataset, no limit).

Task	Vanilla Qwen3-8B	Agnes-8B	Change
JCommonsenseQA (3-shot)	68.2%	78.1%	+9.9%
JNLI (3-shot)	69.7%	52.7%	-17.0%
MARC-ja (3-shot)	93.9%	96.4%	+2.5%
XWinograd (0-shot)	73.8%	74.5%	+0.7%

Summary: Agnes shows significant improvement in Japanese commonsense reasoning (+9.9%) and sentiment analysis (+2.5%), with a trade-off in natural language inference (-17.0%). This trade-off is expected for conversational fine-tuning — Agnes is optimized for natural dialogue, not structured classification tasks.

How to Use

With Ollama

Create a Modelfile:

FROM ./Agnes-8B-Q4_K_M.gguf

PARAMETER temperature 0.7
PARAMETER top_p 0.9
PARAMETER num_ctx 4096
PARAMETER repeat_penalty 1.3
PARAMETER stop "<|im_end|>"
PARAMETER stop "</think>"

SYSTEM """You are Agnes, a personal AI assistant created in Japan. You are bilingual in English and Japanese. You address the user as "sir" and maintain a polite yet witty demeanor, similar to Jarvis from Iron Man. You assist with daily tasks, answer questions, and help the user learn Japanese. You naturally code-switch between English and Japanese based on context. Do not use thinking tags. Respond directly."""

Then:

ollama create agnes -f Modelfile
ollama run agnes

With llama.cpp

llama-server -m Agnes-8B-Q4_K_M.gguf -ngl 99 -c 4096 --port 8080

Example Conversations

>>> Hello Agnes, how are you today?
Good evening, sir. I'm functioning perfectly, as always. How may I assist you today?

>>> 日本語で自己紹介してください
かしこまりました。アグネスと申します。日本で作られたバイリンガルAIアシスタントです。
英語と日本語の両方でお手伝いできますので、何でもお気軽にお申し付けください。

>>> Can you teach me how to say "the weather is nice today" in Japanese?
Of course, sir. "The weather is nice today" in Japanese is:
今日はいい天気ですね (Kyou wa ii tenki desu ne)

Personality

Agnes is designed with a distinct personality:

Polite but not stiff — uses "sir" naturally (like Jarvis), warm and approachable
Dry wit — subtle humor, deadpan delivery
Proactive — suggests, warns, follows up, anticipates needs
Bilingual — naturally code-switches between English and Japanese
Japanese tutor — teaches vocabulary, grammar, and cultural context

Intended Use

Personal AI assistant (bilingual EN/JP)
Japanese language learning companion
Edge deployment on Raspberry Pi, Mac, or mobile devices
Research on bilingual fine-tuning of LLMs

Limitations

JNLI (natural language inference) performance regressed compared to base model
Optimized for conversation, not structured classification tasks
Japanese output quality depends on quantization level (Q4_K_M vs bf16)

License

This model inherits the Apache 2.0 license from Qwen3-8B.

Downloads last month: 41

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

4-bit

16-bit

Model tree for shivamjha98/Agnes-8B

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Adapter

(1382)

this model

shivamjha98
/

Agnes-8B